arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2409.05470eess.SPeess.AS
收藏

基于度量学习的可迁移选择性虚拟传感主动噪声控制技术

Transferable Selective Virtual Sensing Active Noise Control Technique Based on Metric Learning

Boxiang Wang, Dongyuan Shi, Zhengding Luo, Xiaoyi Shen, Junwei Ji, Woon-Seng Gan

AI总结:

针对CNN虚拟传感ANC需随系统重复训练的问题,提出融合度量学习的可迁移选择性VS方法,可直接迁移到新ANC系统并应对未知噪声,仿真验证其降噪效果。

摘要:

虚拟传感(VS)技术使主动噪声控制(ANC)系统能够在远离物理误差麦克风的虚拟位置衰减噪声。合适的辅助滤波器(AF)可以显著增强VS方法的有效性。为不同类型噪声选择合适的AF可利用卷积神经网络(CNN)自动实现。然而,为不同ANC系统训练CNN模型通常耗费人力且耗时。为解决该问题,我们提出一种新方法——可迁移选择性VS,将度量学习技术集成到基于CNN的VS方法中。可迁移选择性VS方法允许预训练CNN直接应用于新的ANC系统,无需重新训练,并且能够处理未见过的噪声类型。数值仿真证明了所提方法在衰减突变宽带噪声和真实世界噪声方面的有效性。

英文摘要:

Virtual sensing (VS) technology enables active noise control (ANC) systems to attenuate noise at virtual locations distant from the physical error microphones. Appropriate auxiliary filters (AF) can significantly enhance the effectiveness of VS approaches. The selection of appropriate AF for various types of noise can be automatically achieved using convolutional neural networks (CNNs). However, training the CNN model for different ANC systems is often labour-intensive and time-consuming. To tackle this problem, we propose a novel method, Transferable Selective VS, by integrating metric-learning technology into CNN-based VS approaches. The Transferable Selective VS method allows a pre-trained CNN to be applied directly to new ANC systems without requiring retraining, and it can handle unseen noise types. Numerical simulations demonstrate the effectiveness of the proposed method in attenuating sudden-varying broadband noises and real-world noises.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑